airbnb = read_csv("airbnb_dataset_parsed_cleaned_uploadable_without_text2.csv")
## Warning: Missing column names filled in: 'X1' [1]
## Parsed with column specification:
## cols(
## .default = col_double(),
## neighbourhood_group = col_character(),
## neighbourhood = col_character(),
## room_type = col_character(),
## bed_type = col_character(),
## amenities = col_character(),
## host_has_profile_pic = col_character(),
## host_verifications = col_character(),
## `Cable TV` = col_logical()
## )
## See spec(...) for full column specifications.
airbnb =
airbnb %>%
filter(review_scores_rating!=0, price>0) %>% mutate(host_has_profile_pic = ifelse(host_has_profile_pic == "t", 1, 0), log_price=log(price))
Column
Chart A
airbnb %>%
mutate(neighbourhood = fct_reorder(neighbourhood, log_price)) %>%
plot_ly(y = ~log(price), color = ~neighbourhood, type = "box",
colors = "Set2")
Chart B
airbnb %>%
count(neighbourhood_group) %>%
mutate(neighbourhood = fct_reorder(neighbourhood_group, n)) %>%
plot_ly(x = ~neighbourhood_group, y = ~n, color = ~neighbourhood_group, type = "bar")
Column
Chart C
airbnb %>%
mutate(text_label = str_c("Price: $", price, '\nNeighborhood:', neighbourhood, '\nType: ', room_type, '\nNo. of Reviews: ',number_of_reviews)) %>%
plot_ly(x = ~review_scores_rating, y = ~log_price, type = "box",
color = ~room_type, text = ~text_label, alpha = 0.4)
Chart D
airbnb %>%
mutate(text_label = str_c("Price: $", price, '\nNeighborhood:', neighbourhood, '\nType: ', room_type, '\nNo. of Reviews: ',number_of_reviews)) %>%
plot_ly(x = ~amenities2, y = ~log_price, type = "scatter", mode='markers', color = ~room_type, text = ~text_label, alpha = 0.4)